无法同时起用 torch gpu和paddlepaddle gpu加速

[albin3]

Description of the bug | 错误描述

一旦安装panddlepaddle-gpu就会包segmentation错误

2024-08-10 19:05:37.999 | INFO     | magic_pdf.libs.pdf_check:detect_invalid_chars:57 - cid_count: 0, text_len: 8, cid_chars_radio: 0.0
2024-08-10 19:05:38.001 | WARNING  | magic_pdf.filter.pdf_classify_by_type:classify:334 - pdf is not classified by area and text_len, by_image_area: False, by_text: False, by_avg_words: False, by_img_num: True, by_text_layout: False, by_img_narrow_strips: False, by_invalid_chars: True
INFO:datasets:PyTorch version 2.3.1 available.
2024-08-10 19:05:43.181 | WARNING  | magic_pdf.libs.config_reader:get_table_recog_config:84 - 'table-config' not found in magic-pdf.json, use 'False' as default
2024-08-10 19:05:43.183 | INFO     | magic_pdf.model.pdf_extract_kit:__init__:111 - DocAnalysis init, this may take some times. apply_layout: True, apply_formula: True, apply_ocr: True, apply_table: False
2024-08-10 19:05:43.183 | INFO     | magic_pdf.model.pdf_extract_kit:__init__:119 - using device: cuda
2024-08-10 19:05:43.183 | INFO     | magic_pdf.model.pdf_extract_kit:__init__:121 - using models_dir: ./PDF-Extract-Kit/models/
CustomVisionEncoderDecoderModel init
CustomMBartForCausalLM init
CustomMBartDecoder init
[08/10 19:06:08 detectron2]: Rank of current process: 0. World size: 1
cuobjdump info    : File '/tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/detectron2/_C.cpython-310-x86_64-linux-gnu.so' does not contain device code
[08/10 19:06:09 detectron2]: Environment info:
-------------------------------  --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
sys.platform                     linux
Python                           3.10.9 (main, Mar  1 2023, 18:23:06) [GCC 11.2.0]
numpy                            1.26.4
detectron2                       0.6 @/tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/detectron2
detectron2._C                    not built correctly: /lib64/libc.so.6: version `GLIBC_2.32' not found (required by /tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/detectron2/_C.cpython-310-x86_64-linux-gnu.so)
Compiler ($CXX)                  c++ (GCC) 4.8.5 20150623 (Red Hat 4.8.5-39)
CUDA compiler                    Build cuda_12.1.r12.1/compiler.32688072_0
detectron2 arch flags            /tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/detectron2/_C.cpython-310-x86_64-linux-gnu.so
DETECTRON2_ENV_MODULE            <not set>
PyTorch                          2.3.1+cu121 @/tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/torch
PyTorch debug build              False
torch._C._GLIBCXX_USE_CXX11_ABI  False
GPU available                    Yes
GPU 0                            NVIDIA A10 (arch=8.6)
Driver version                   470.82.01
CUDA_HOME                        /usr/local/cuda
Pillow                           10.4.0
torchvision                      0.18.1+cu121 @/tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/torchvision
torchvision arch flags           5.0, 6.0, 7.0, 7.5, 8.0, 8.6, 9.0
fvcore                           0.1.5.post20221221
iopath                           0.1.9
cv2                              4.6.0
-------------------------------  --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX512
  - CUDA Runtime 12.1
  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
  - CuDNN 8.9.3
    - Built with CuDNN 8.9.2
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.9.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.3.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, 

[08/10 19:06:09 detectron2]: Command line arguments: {'config_file': '/tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml', 'resume': False, 'eval_only': False, 'num_gpus': 1, 'num_machines': 1, 'machine_rank': 0, 'dist_url': 'tcp://127.0.0.1:57823', 'opts': ['MODEL.WEIGHTS', './PDF-Extract-Kit/models/Layout/model_final.pth']}
[08/10 19:06:09 detectron2]: Contents of args.config_file=/tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml:
AUG:
  DETR: true
CACHE_DIR: ~/cache/huggingface
CUDNN_BENCHMARK: false
DATALOADER:
  ASPECT_RATIO_GROUPING: true
  FILTER_EMPTY_ANNOTATIONS: false
  NUM_WORKERS: 4
  REPEAT_THRESHOLD: 0.0
  SAMPLER_TRAIN: TrainingSampler
DATASETS:
  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
  PROPOSAL_FILES_TEST: []
  PROPOSAL_FILES_TRAIN: []
  TEST:
  - scihub_train
  TRAIN:
  - scihub_train
GLOBAL:
  HACK: 1.0
ICDAR_DATA_DIR_TEST: ''
ICDAR_DATA_DIR_TRAIN: ''
INPUT:
  CROP:
    ENABLED: true
    SIZE:
    - 384
    - 600
    TYPE: absolute_range
  FORMAT: RGB
  MASK_FORMAT: polygon
  MAX_SIZE_TEST: 1333
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_TEST: 800
  MIN_SIZE_TRAIN:
  - 480
  - 512
  - 544
  - 576
  - 608
  - 640
  - 672
  - 704
  - 736
  - 768
  - 800
  MIN_SIZE_TRAIN_SAMPLING: choice
  RANDOM_FLIP: horizontal
MODEL:
  ANCHOR_GENERATOR:
    ANGLES:
    - - -90
      - 0
      - 90
    ASPECT_RATIOS:
    - - 0.5
      - 1.0
      - 2.0
    NAME: DefaultAnchorGenerator
    OFFSET: 0.0
    SIZES:
    - - 32
    - - 64
    - - 128
    - - 256
    - - 512
  BACKBONE:
    FREEZE_AT: 2
    NAME: build_vit_fpn_backbone
  CONFIG_PATH: ''
  DEVICE: cuda
  FPN:
    FUSE_TYPE: sum
    IN_FEATURES:
    - layer3
    - layer5
    - layer7
    - layer11
    NORM: ''
    OUT_CHANNELS: 256
  IMAGE_ONLY: true
  KEYPOINT_ON: false
  LOAD_PROPOSALS: false
  MASK_ON: true
  META_ARCHITECTURE: VLGeneralizedRCNN
  PANOPTIC_FPN:
    COMBINE:
      ENABLED: true
      INSTANCES_CONFIDENCE_THRESH: 0.5
      OVERLAP_THRESH: 0.5
      STUFF_AREA_LIMIT: 4096
    INSTANCE_LOSS_WEIGHT: 1.0
  PIXEL_MEAN:
  - 127.5
  - 127.5
  - 127.5
  PIXEL_STD:
  - 127.5
  - 127.5
  - 127.5
  PROPOSAL_GENERATOR:
    MIN_SIZE: 0
    NAME: RPN
  RESNETS:
    DEFORM_MODULATED: false
    DEFORM_NUM_GROUPS: 1
    DEFORM_ON_PER_STAGE:
    - false
    - false
    - false
    - false
    DEPTH: 50
    NORM: FrozenBN
    NUM_GROUPS: 1
    OUT_FEATURES:
    - res4
    RES2_OUT_CHANNELS: 256
    RES5_DILATION: 1
    STEM_OUT_CHANNELS: 64
    STRIDE_IN_1X1: true
    WIDTH_PER_GROUP: 64
  RETINANET:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_WEIGHTS:
    - 1.0
    - 1.0
    - 1.0
    - 1.0
    FOCAL_LOSS_ALPHA: 0.25
    FOCAL_LOSS_GAMMA: 2.0
    IN_FEATURES:
    - p3
    - p4
    - p5
    - p6
    - p7
    IOU_LABELS:
    - 0
    - -1
    - 1
    IOU_THRESHOLDS:
    - 0.4
    - 0.5
    NMS_THRESH_TEST: 0.5
    NORM: ''
    NUM_CLASSES: 10
    NUM_CONVS: 4
    PRIOR_PROB: 0.01
    SCORE_THRESH_TEST: 0.05
    SMOOTH_L1_LOSS_BETA: 0.1
    TOPK_CANDIDATES_TEST: 1000
  ROI_BOX_CASCADE_HEAD:
    BBOX_REG_WEIGHTS:
    - - 10.0
      - 10.0
      - 5.0
      - 5.0
    - - 20.0
      - 20.0
      - 10.0
      - 10.0
    - - 30.0
      - 30.0
      - 15.0
      - 15.0
    IOUS:
    - 0.5
    - 0.6
    - 0.7
  ROI_BOX_HEAD:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS:
    - 10.0
    - 10.0
    - 5.0
    - 5.0
    CLS_AGNOSTIC_BBOX_REG: true
    CONV_DIM: 256
    FC_DIM: 1024
    NAME: FastRCNNConvFCHead
    NORM: ''
    NUM_CONV: 0
    NUM_FC: 2
    POOLER_RESOLUTION: 7
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
    SMOOTH_L1_BETA: 0.0
    TRAIN_ON_PRED_BOXES: false
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 512
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    IOU_LABELS:
    - 0
    - 1
    IOU_THRESHOLDS:
    - 0.5
    NAME: CascadeROIHeads
    NMS_THRESH_TEST: 0.5
    NUM_CLASSES: 10
    POSITIVE_FRACTION: 0.25
    PROPOSAL_APPEND_GT: true
    SCORE_THRESH_TEST: 0.05
  ROI_KEYPOINT_HEAD:
    CONV_DIMS:
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    LOSS_WEIGHT: 1.0
    MIN_KEYPOINTS_PER_IMAGE: 1
    NAME: KRCNNConvDeconvUpsampleHead
    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
    NUM_KEYPOINTS: 17
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  ROI_MASK_HEAD:
    CLS_AGNOSTIC_MASK: false
    CONV_DIM: 256
    NAME: MaskRCNNConvUpsampleHead
    NORM: ''
    NUM_CONV: 4
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  RPN:
    BATCH_SIZE_PER_IMAGE: 256
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS:
    - 1.0
    - 1.0
    - 1.0
    - 1.0
    BOUNDARY_THRESH: -1
    CONV_DIMS:
    - -1
    HEAD_NAME: StandardRPNHead
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    - p6
    IOU_LABELS:
    - 0
    - -1
    - 1
    IOU_THRESHOLDS:
    - 0.3
    - 0.7
    LOSS_WEIGHT: 1.0
    NMS_THRESH: 0.7
    POSITIVE_FRACTION: 0.5
    POST_NMS_TOPK_TEST: 1000
    POST_NMS_TOPK_TRAIN: 2000
    PRE_NMS_TOPK_TEST: 1000
    PRE_NMS_TOPK_TRAIN: 2000
    SMOOTH_L1_BETA: 0.0
  SEM_SEG_HEAD:
    COMMON_STRIDE: 4
    CONVS_DIM: 128
    IGNORE_VALUE: 255
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    LOSS_WEIGHT: 1.0
    NAME: SemSegFPNHead
    NORM: GN
    NUM_CLASSES: 10
  VIT:
    DROP_PATH: 0.1
    IMG_SIZE:
    - 224
    - 224
    NAME: layoutlmv3_base
    OUT_FEATURES:
    - layer3
    - layer5
    - layer7
    - layer11
    POS_TYPE: abs
  WEIGHTS: 
OUTPUT_DIR: 
SCIHUB_DATA_DIR_TRAIN: ~/publaynet/layout_scihub/train
SEED: 42
SOLVER:
  AMP:
    ENABLED: true
  BACKBONE_MULTIPLIER: 1.0
  BASE_LR: 0.0002
  BIAS_LR_FACTOR: 1.0
  CHECKPOINT_PERIOD: 2000
  CLIP_GRADIENTS:
    CLIP_TYPE: full_model
    CLIP_VALUE: 1.0
    ENABLED: true
    NORM_TYPE: 2.0
  GAMMA: 0.1
  GRADIENT_ACCUMULATION_STEPS: 1
  IMS_PER_BATCH: 32
  LR_SCHEDULER_NAME: WarmupCosineLR
  MAX_ITER: 20000
  MOMENTUM: 0.9
  NESTEROV: false
  OPTIMIZER: ADAMW
  REFERENCE_WORLD_SIZE: 0
  STEPS:
  - 10000
  WARMUP_FACTOR: 0.01
  WARMUP_ITERS: 333
  WARMUP_METHOD: linear
  WEIGHT_DECAY: 0.05
  WEIGHT_DECAY_BIAS: null
  WEIGHT_DECAY_NORM: 0.0
TEST:
  AUG:
    ENABLED: false
    FLIP: true
    MAX_SIZE: 4000
    MIN_SIZES:
    - 400
    - 500
    - 600
    - 700
    - 800
    - 900
    - 1000
    - 1100
    - 1200
  DETECTIONS_PER_IMAGE: 100
  EVAL_PERIOD: 1000
  EXPECTED_RESULTS: []
  KEYPOINT_OKS_SIGMAS: []
  PRECISE_BN:
    ENABLED: false
    NUM_ITER: 200
VERSION: 2
VIS_PERIOD: 0

[08/10 19:06:10 d2.checkpoint.detection_checkpoint]: [DetectionCheckpointer] Loading from ./PDF-Extract-Kit/models/Layout/model_final.pth ...
[08/10 19:06:10 fvcore.common.checkpoint]: [Checkpointer] Loading from ./PDF-Extract-Kit/models/Layout/model_final.pth ...
2024-08-10 19:06:13.969 | INFO     | magic_pdf.model.pdf_extract_kit:__init__:152 - DocAnalysis init done!
2024-08-10 19:06:13.969 | INFO     | magic_pdf.model.doc_analyze_by_custom_model:custom_model_init:98 - model init cost: 35.96749496459961

--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0   at::_ops::conv2d::call(at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::SymInt)
1   at::native::conv2d_symint(at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::SymInt)
2   at::_ops::convolution::call(at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, bool, c10::ArrayRef<c10::SymInt>, c10::SymInt)
3   at::_ops::convolution::redispatch(c10::DispatchKeySet, at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, bool, c10::ArrayRef<c10::SymInt>, c10::SymInt)
4   at::native::convolution(at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, c10::ArrayRef<long>, c10::ArrayRef<long>, c10::ArrayRef<long>, bool, c10::ArrayRef<long>, long)
5   at::_ops::_convolution::call(at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, bool, c10::ArrayRef<c10::SymInt>, c10::SymInt, bool, bool, bool, bool)
6   at::native::_convolution(at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, c10::ArrayRef<long>, c10::ArrayRef<long>, c10::ArrayRef<long>, bool, c10::ArrayRef<long>, long, bool, bool, bool, bool)
7   at::_ops::cudnn_convolution::call(at::Tensor const&, at::Tensor const&, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::ArrayRef<c10::SymInt>, c10::SymInt, bool, bool, bool)
8   at::native::cudnn_convolution(at::Tensor const&, at::Tensor const&, c10::ArrayRef<long>, c10::ArrayRef<long>, c10::ArrayRef<long>, long, bool, bool, bool)

----------------------
Error Message Summary:
----------------------
FatalError: `Segmentation fault` is detected by the operating system.
  [TimeInfo: *** Aborted at 1723287977 (unix time) try "date -d @1723287977" if you are using GNU date ***]
  [SignalInfo: *** SIGSEGV (@0x20000002eea) received by PID 383111 (TID 0x7ffa4c1e6740) from PID 12010 ***]

Segmentation fault

How to reproduce the bug | 如何复现

在centos7.2中按照文档安装

Operating system | 操作系统

Linux

Python version | Python 版本

3.10

Software version | 软件版本 (magic-pdf --version)

0.6.x

Device mode | 设备模式

cuda

[albin3]

cuobjdump info    : File '/tmp/mineru_magong/xxx/python/lib/conda/lib/python3.10/site-packages/detectron2/_C.cpython-310-x86_64-linux-gnu.so' does not contain device code

这个日志信息是否正常？

[myhloli]

linux系统下torch和paddle同时加速我们目前只保证在Ubuntu22.04LTS下稳定可用，其他系统暂时没办法测试。具体可参考readme文档中设备平台支持一节。

[albin3]

版本是 magic-pdf[full]==0.7.0b1

[albin3]

@myhloli 我没找到ubuntu的环境，帮忙看下ubuntu中有类似cuobjdump info 这种warning么？

[myhloli]

你的问题应该和detectron2无关，能给你的建议是参考https://github.com/opendatalab/MinerU/blob/master/docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md 这篇文档，确认自己是在8，9，10中的哪一步遇到报错，来定位兼容性问题出现在cpu，torch还是paddle

[albin3]

8、9没问题，第10步操作以后会导致第9步报错（不管是不是走ocr还是txt模式）

[myhloli]

有可能是paddle不兼容，而且引入了新的cuda依赖导致torch的环境失效，建议只使用torch加速，paddle使用cpu版本。如果一定要同时使用加速的话，还请安装ubuntu22.04系统。

[albin3]

cpu实在有点慢

你在Ubuntu里解决这个问题的时候有啥思路或者文档参考么？

我想在centos是解决试试。要是搞定了反馈给你们

[myhloli]

没什么特别好的思路，一就是排列组合，cuda，torch，paddle这三个控制变量，换着不同的版本装了再测试，总能找到一个稳定同时加速的版本，你这个我看driver版本470可能有点低，要不试试升级到530以上看看

[myhloli]

对你来说，比较简单的方式可能是试试基于Ubuntu镜像的docker，可能可以少走弯路一步到位

[albin3]

通过对比多次安装的site-packages所有文件解决

centos可以启动了，操作步骤：

1. pip install magic-pdf[full]==0.7.0b1 --extra-index-url https://wheels.myhloli.com -i https://pypi.tuna.tsinghua.edu.cn/simple
2. python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/

不出意外的话此时会出现 C++ Traceback (most recent call last): 报错

3. 此时复制 site-packages 中的 paddle 目录到 /tmp/
4. 重新安装  magic-pdf： pip install magic-pdf[full]==0.7.0b1 --extra-index-url https://wheels.myhloli.com -i https://pypi.tuna.tsinghua.edu.cn/simple

安装完成后，解析任何pdf都不会走paddlepaddle-gpu （即，跟第一步装完的效果相同）

即解除了 C++ Traceback (most recent call last):  的报错，但不会走ocr的gpu加速

5. 将 /tmp/paddle 目录复制并覆盖 site-packages/paddle

再解析需要ocr的pdf，就会同时走 paddlepaddle-gpu + torch